Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add not0lucky/tubescout --skill yt-validategit clone --depth 1 https://github.com/not0lucky/tubescoutWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/not0lucky/tubescout/yt-validate)<a href="https://agentmods.dev/skills/not0lucky/tubescout/yt-validate"><img src="https://agentmods.dev/badge/skills/not0lucky/tubescout/yt-validate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/not0lucky/tubescout/yt-validate"><img src="https://agentmods.dev/badge/skills/not0lucky/tubescout/yt-validate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.00660 |
| Opus 5 | $0.00038 | $0.00330 |
| Sonnet 5 | $0.00015 | $0.00132 |
| Haiku 4.5 | $0.00008 | $0.00066 |
Grade A, and why
yt-validate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
yt-validate
A fast, evidence-based saturation-and-demand check. The output is a verdict with receipts, not encouragement.
Process
- Demand.
get_search_suggestionson the idea's core terms (the noun people would search, not the product name). Rich, specific suggestions = real search demand; empty/generic = weak signal (note: absence of YouTube demand ≠ no market — some B2B niches don't live on YouTube; say so when relevant). - Saturation.
search_videosfor the idea and its category:- How many videos directly cover it? How recent? (
uploadDate: year) - Are there "$X/month with " case studies already? How many creators?
get_videoon the top 2–3: views, publish dates, engagement. A crowded case-study field means the wave is late-stage; a few strong recent ones mean it's validated but open; none means unproven (which cuts both ways).
- How many videos directly cover it? How recent? (
- Ground truth.
get_transcripton the 2–3 most substantive competitor/case-study videos. Extract: actual revenue evidence, what the incumbents do badly, complaints in passing, and how hard the thing was to build/distribute. - Verdict. One of: validated-and-open / validated-but-crowded / unproven / crowded-and-late. State the 2–3 facts that drove it, what would change it, and the cheapest next test the user could run. Where the conversation reveals the user's assets (existing skills, infra, audience, distribution), weigh them: "crowded" can still be a yes for someone with an unfair advantage the incumbents lack — name it explicitly when that applies.
Rules
- Cite only URLs returned by tubescout tools in this conversation — never write a YouTube URL or video ID from memory.
- Timestamps matter: a 2024 gold rush may be a 2026 graveyard. Weight recent evidence.
- Distinguish "many videos about X" (education demand — good) from "many products doing X" (competition — check both).
- If the evidence is thin, say "thin evidence", not a hedged maybe-verdict.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 45 lines · 76 tokens per session scan A 24677dfad284
yt-validate is a skill published in the GitHub repository not0lucky/tubescout (0 stars, last pushed 16d ago), licensed MIT. It adds 76 tokens to every session and 660 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
youtube-research
Research topics across YouTube videos efficiently using Scribefy's MCP tools — search for candidates, vet them with free metadata before spending credits, extract transcripts selectively, and synthesize timestamped answers. Use when researching a topic on YouTube, summarizing or comparing videos, pulling quotes or…
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
client-scripts
Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.
split-to-prs
Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.
agreement-setup
Set up a bKash tokenized agreement for repeat charges and check its status.
planfix-api
A Planfix CRM integration for managing tasks and contacts. A CRM is a system for organizing customer and business relationships.